[pre-commit.ci] pre-commit autoupdate

.pre-commit-config.yaml

@@ -1,11 +1,11 @@
 exclude: '\.(tsv|fasta|gb)$|^shared/vendored/|^phylogenetic/rules/config.smk'
 repos:
   - repo: https://github.com/snakemake/snakefmt
-    rev: v0.11.1
+    rev: v2.0.3
     hooks:
       - id: snakefmt
   - repo: https://github.com/rhysd/actionlint
-    rev: v1.7.7
+    rev: v1.7.12
     hooks:
       - id: actionlint
         entry: env SHELLCHECK_OPTS='--exclude=SC2027' actionlint
@@ -16,11 +16,11 @@ repos:
   #       additional_dependencies:
   #         - tomli
   - repo: https://github.com/google/yamlfmt
-    rev: v0.17.2
+    rev: v0.21.0
     hooks:
       - id: yamlfmt
   - repo: https://github.com/pappasam/toml-sort
-    rev: v0.24.2
+    rev: v0.24.4
     hooks:
       - id: toml-sort-fix
   - repo: https://github.com/pre-commit/pre-commit-hooks
@@ -42,7 +42,7 @@ repos:
       - id: end-of-file-fixer
       - id: fix-byte-order-marker
   - repo: https://github.com/pre-commit/sync-pre-commit-deps
-    rev: v0.0.3
+    rev: v0.0.4
     hooks:
       - id: sync-pre-commit-deps
   - repo: https://github.com/shellcheck-py/shellcheck-py

ingest/Snakefile

@@ -27,7 +27,11 @@ rule all:
 
 
 include: "rules/curate.smk"
+
+
 include: "rules/nextclade.smk"
+
+
 include: "rules/fetch_from_ppx.smk"
 
 
@@ -44,18 +48,18 @@ if "custom_rules" in config:
 
 
 rule extract_open_data:
-    input:
-        metadata="results/metadata.tsv",
-        sequences="results/sequences.fasta",
-    output:
-        metadata="results/metadata_open.tsv",
-        sequences="results/sequences_open.fasta",
-    shell:
-        """
-        augur filter --metadata {input.metadata} \
-                     --sequences {input.sequences} \
-                     --metadata-id-columns PPX_accession \
-                     --exclude-where "dataUseTerms=RESTRICTED" \
-                     --output-metadata {output.metadata} \
-                     --output-sequences {output.sequences}
-        """
+        input:
+            metadata="results/metadata.tsv",
+            sequences="results/sequences.fasta",
+        output:
+            metadata="results/metadata_open.tsv",
+            sequences="results/sequences_open.fasta",
+        shell:
+            """
+            augur filter --metadata {input.metadata} \
+                --sequences {input.sequences} \
+                --metadata-id-columns PPX_accession \
+                --exclude-where "dataUseTerms=RESTRICTED" \
+                --output-metadata {output.metadata} \
+                --output-sequences {output.sequences}
+            """

ingest/build-configs/nextstrain-automation/nextstrain_automation.smk

@@ -63,20 +63,20 @@ rule custom_subset_metadata:
         metadata="data/all_metadata_added.tsv",
     output:
         subset_metadata="data/subset_metadata.tsv",
-    params:
-        metadata_fields=",".join(config["curate"]["metadata_columns"]),
-    benchmark:
-        "benchmarks/subset_metadata.txt"
     log:
         "logs/subset_metadata.txt",
+    benchmark:
+        "benchmarks/subset_metadata.txt"
+    params:
+        metadata_fields=",".join(config["curate"]["metadata_columns"]),
     shell:
         r"""
         exec &> >(tee {log:q})
 
         csvtk cut -t -f {params.metadata_fields:q} \
             {input.metadata:q} \
             | csvtk mutate -t -f date_released -n date_submitted \
-            > {output.subset_metadata:q}
+                >{output.subset_metadata:q}
         """
 
 

phylogenetic/rules/annotate_phylogeny.smk

@@ -29,17 +29,17 @@ rule ancestral:
         alignment=build_dir + "/{build_name}/masked.fasta",
     output:
         node_data=build_dir + "/{build_name}/nt_muts.json",
+    log:
+        "logs/{build_name}/ancestral.txt",
+    benchmark:
+        "benchmarks/{build_name}/ancestral.txt"
     params:
         inference="joint",
         root_sequence=lambda w: (
             ("--root-sequence " + config["ancestral_root_seq"])
             if config.get("ancestral_root_seq")
             else ""
         ),
-    log:
-        "logs/{build_name}/ancestral.txt",
-    benchmark:
-        "benchmarks/{build_name}/ancestral.txt"
     shell:
         r"""
         exec &> >(tee {log:q})
@@ -83,20 +83,21 @@ rule traits:
     """
     Inferring ancestral traits for {params.columns!s}
       - increase uncertainty of reconstruction by {params.sampling_bias_correction} to partially account for sampling bias
+
     """
     input:
         tree=build_dir + "/{build_name}/tree.nwk",
         metadata=build_dir + "/{build_name}/metadata.tsv",
     output:
         node_data=build_dir + "/{build_name}/traits.json",
-    params:
-        columns=config["traits"]["columns"],
-        sampling_bias_correction=config["traits"]["sampling_bias_correction"],
-        strain_id=config["strain_id_field"],
     log:
         "logs/{build_name}/traits.txt",
     benchmark:
         "benchmarks/{build_name}/traits.txt"
+    params:
+        columns=config["traits"]["columns"],
+        sampling_bias_correction=config["traits"]["sampling_bias_correction"],
+        strain_id=config["strain_id_field"],
     shell:
         r"""
         exec &> >(tee {log:q})
@@ -188,12 +189,12 @@ rule recency:
         metadata=build_dir + "/{build_name}/metadata.tsv",
     output:
         node_data=build_dir + "/{build_name}/recency.json",
-    params:
-        strain_id=config["strain_id_field"],
     log:
         "logs/{build_name}/recency.txt",
     benchmark:
         "benchmarks/{build_name}/recency.txt"
+    params:
+        strain_id=config["strain_id_field"],
     shell:
         r"""
         exec &> >(tee {log:q})

phylogenetic/rules/export.smk

@@ -56,12 +56,12 @@ rule colors:
         metadata=build_dir + "/{build_name}/metadata.tsv",
     output:
         colors=build_dir + "/{build_name}/colors.tsv",
-    params:
-        ignore_categories=config.get("colors", {}).get("ignore_categories", []),
     log:
         "logs/{build_name}/colors.txt",
     benchmark:
         "benchmarks/{build_name}/colors.txt"
+    params:
+        ignore_categories=config.get("colors", {}).get("ignore_categories", []),
     shell:
         r"""
         exec &> >(tee {log:q})
@@ -108,12 +108,12 @@ rule export:
     output:
         auspice_json=build_dir + "/{build_name}/tree.json",
         root_sequence=build_dir + "/{build_name}/tree_root-sequence.json",
-    params:
-        strain_id=config["strain_id_field"],
     log:
         "logs/{build_name}/export.txt",
     benchmark:
         "benchmarks/{build_name}/export.txt"
+    params:
+        strain_id=config["strain_id_field"],
     shell:
         r"""
         exec &> >(tee {log:q})

phylogenetic/rules/merge_inputs.smk

@@ -98,7 +98,7 @@ if len(_input_metadata) == 1:
             r"""
             exec &> >(tee {log:q})
 
-            augur read-file {input.metadata:q} > {output.metadata:q}
+            augur read-file {input.metadata:q} >{output.metadata:q}
             """
 
 else:
@@ -114,15 +114,15 @@ else:
                 for name, info in input_sources.items()
                 if info.get("metadata", None)
             },
-        params:
-            metadata=lambda w, input: list(map("=".join, input.items())),
-            id_field=config["strain_id_field"],
         output:
             metadata="results/metadata.tsv",
         log:
             "logs/merge_metadata.txt",
         benchmark:
             "benchmarks/merge_metadata.txt"
+        params:
+            metadata=lambda w, input: list(map("=".join, input.items())),
+            id_field=config["strain_id_field"],
         shell:
             r"""
             exec &> >(tee {log:q})
@@ -154,7 +154,7 @@ if len(_input_sequences) == 1:
             r"""
             exec &> >(tee {log:q})
 
-            augur read-file {input.sequences:q} > {output.sequences:q}
+            augur read-file {input.sequences:q} >{output.sequences:q}
             """
 
 else:

phylogenetic/rules/prepare_sequences.smk

@@ -31,12 +31,12 @@ rule map_accessions:
         script="scripts/map_accessions.py",
     output:
         accession_list=build_dir + "/{build_name}/{in_ex_clude}_ppx.txt",
-    wildcard_constraints:
-        in_ex_clude="(include|exclude)",
     log:
         "logs/{build_name}/map_accessions_{in_ex_clude}.txt",
     benchmark:
         "benchmarks/{build_name}/map_accessions_{in_ex_clude}.txt"
+    wildcard_constraints:
+        in_ex_clude="(include|exclude)",
     shell:
         r"""
         exec &> >(tee {log:q})
@@ -60,6 +60,10 @@ rule filter:
         sequences=build_dir + "/{build_name}/good_sequences.fasta",
         metadata=build_dir + "/{build_name}/good_metadata.tsv",
         log=build_dir + "/{build_name}/good_filter.log",
+    log:
+        "logs/{build_name}/filter.txt",
+    benchmark:
+        "benchmarks/{build_name}/download.txt"
     params:
         min_date=config["filter"]["min_date"],
         min_length=config["filter"]["min_length"],
@@ -70,10 +74,6 @@ rule filter:
             if "exclude_where" in config["filter"]
             else ""
         ),
-    log:
-        "logs/{build_name}/filter.txt",
-    benchmark:
-        "benchmarks/{build_name}/download.txt"
     shell:
         r"""
         exec &> >(tee {log:q})
@@ -135,13 +135,13 @@ rule subsample:
     output:
         strains=build_dir + "/{build_name}/{sample}_strains.txt",
         log=build_dir + "/{build_name}/{sample}_filter.log",
-    params:
-        augur_filter_args=lambda w: config["subsample"][w.sample],
-        strain_id=config["strain_id_field"],
     log:
         "logs/{build_name}/{sample}_subsample.txt",
     benchmark:
         "benchmarks/{build_name}/{sample}_subsample.txt"
+    params:
+        augur_filter_args=lambda w: config["subsample"][w.sample],
+        strain_id=config["strain_id_field"],
     shell:
         r"""
         exec &> >(tee {log:q})
@@ -175,12 +175,12 @@ rule combine_samples:
     output:
         sequences=build_dir + "/{build_name}/filtered.fasta",
         metadata=build_dir + "/{build_name}/metadata.tsv",
-    params:
-        strain_id=config["strain_id_field"],
     log:
         "logs/{build_name}/combine_samples.txt",
     benchmark:
         "benchmarks/{build_name}/combine_samples.txt"
+    params:
+        strain_id=config["strain_id_field"],
     shell:
         r"""
         exec &> >(tee {log:q})
@@ -190,8 +190,7 @@ rule combine_samples:
             --sequences {input.sequences:q} \
             --metadata {input.metadata:q} \
             --exclude-all \
-            --include {input.strains:q} {input.include:q}\
-            --output-sequences {output.sequences:q} \
+            --include {input.strains:q} {input.include:q} --output-sequences {output.sequences:q} \
             --output-metadata {output.metadata:q}
         """
 
@@ -206,6 +205,11 @@ rule align:
         genome_annotation=config["genome_annotation"],
     output:
         alignment=build_dir + "/{build_name}/aligned.fasta",
+    log:
+        "logs/{build_name}/align.txt",
+    benchmark:
+        "benchmarks/{build_name}/align.txt"
+    threads: workflow.cores
     params:
         # Alignment params from all-clades nextclade dataset
         excess_bandwidth=100,
@@ -214,11 +218,6 @@ rule align:
         min_seed_cover=0.1,
         allowed_mismatches=8,
         gap_alignment_side="left",
-    threads: workflow.cores
-    log:
-        "logs/{build_name}/align.txt",
-    benchmark:
-        "benchmarks/{build_name}/align.txt"
     shell:
         r"""
         exec &> >(tee {log:q})
@@ -235,7 +234,7 @@ rule align:
             --gap-alignment-side {params.gap_alignment_side:q} \
             --output-fasta - \
             {input.sequences:q} \
-            | seqkit seq -i > {output.alignment:q}
+            | seqkit seq -i >{output.alignment:q}
         """
 
 
@@ -250,13 +249,13 @@ rule mask:
         mask=config["mask"]["maskfile"],
     output:
         build_dir + "/{build_name}/masked.fasta",
-    params:
-        from_start=config["mask"]["from_beginning"],
-        from_end=config["mask"]["from_end"],
     log:
         "logs/{build_name}/mask.txt",
     benchmark:
         "benchmarks/{build_name}/mask.txt"
+    params:
+        from_start=config["mask"]["from_beginning"],
+        from_end=config["mask"]["from_end"],
     shell:
         r"""
         exec &> >(tee {log:q})